Quickest Detection of Intermittent Signals With Application to Vision Based Aircraft Detection
This work addresses the problem of detecting intermittent signals for safety-critical applications like aircraft detection, offering a theoretically grounded rule with performance gains.
The authors propose a quickest detection rule for intermittent signals that switch between normal and anomalous states, demonstrating improvements in detection range and false alarm rates over state-of-the-art methods in vision-based aircraft detection.
In this paper we consider the problem of quickly detecting changes in an intermittent signal that can (repeatedly) switch between a normal and an anomalous state. We pose this intermittent signal detection problem as an optimal stopping problem and establish a quickest intermittent signal detection (ISD) rule with a threshold structure. We develop bounds to characterise the performance of our ISD rule and establish a new filter for estimating its detection delays. Finally, we examine the performance of our ISD rule in both a simulation study and an important vision based aircraft detection application where the ISD rule demonstrates improvements in detection range and false alarm rates relative to the current state of the art aircraft detection techniques.