Sequential Score Adaptation with Extreme Value Theory for Robust Railway Track Inspection

TL;DR

This paper introduces a novel method using extreme value theory within a Bayesian framework to adaptively adjust anomaly detector sensitivity, significantly reducing false alarms and improving defect detection in railway track inspections.

Contribution

It proposes a new score adaptation technique based on EVT and Bayesian inference to enhance the robustness of machine vision-based track inspection systems.

Findings

Increased defect detection rate from 95.40% to 99.26% at PFA 0.1%

Reduced variability in false alarm rates under varying conditions

Effective application on a large real-world railway dataset

Abstract

Periodic inspections are necessary to keep railroad tracks in state of good repair and prevent train accidents. Automatic track inspection using machine vision technology has become a very effective inspection tool. Because of its non-contact nature, this technology can be deployed on virtually any railway vehicle to continuously survey the tracks and send exception reports to track maintenance personnel. However, as appearance and imaging conditions vary, false alarm rates can dramatically change, making it difficult to select a good operating point. In this paper, we use extreme value theory (EVT) within a Bayesian framework to optimally adjust the sensitivity of anomaly detectors. We show that by approximating the lower tail of the probability density function (PDF) of the scores with an Exponential distribution (a special case of the Generalized Pareto distribution), and using the Gamma conjugate prior learned from the training data, it is possible to reduce the variability in false alarm rate and improve the overall performance. This method has shown an increase in the defect detection rate of rail fasteners in the presence of clutter (at PFA 0.1%) from 95.40% to 99.26% on the 85-mile Northeast Corridor (NEC) 2012-2013 concrete tie dataset.